johannah Goto Github PK

acn

Implementation of Associative Compression Networks for Representation Learning

add-frame-image

alphazero_gomoku

An implementation of the AlphaZero algorithm for Gomoku (also called Gobang or Five in a Row)

asv

Autonomous surface vehicle

attentive-neural-processes

Repo for learning about nps

balloon-learning-environment

The Balloon Learning Environment - flying stratospheric balloons with deep reinforcement learning.

baselines-rudder

RUDDER for ATARI games with delayed rewards in OpenAI Baselines package

bootstrap_dqn

Implementation of Bootstrap DQN and Randomized Prior Functions on ALE

borealblizzard.github.io

my website that may or may not die

buoyant

Grab data from buoys around the world

cartographer_ros

Provides ROS integration for Cartographer.

climatenet

Climate Analytics using Deep Neural Networks in Python.

clipasso

conditional-neural-process

configs

Configs for different programs

cpc_audio

An implementation of the Contrast Predictive Coding (CPC) method to train audio features in an unsupervised fashion.

crfasrnn

This repository contains the source code for the semantic image segmentation method described in the ICCV 2015 paper: Conditional Random Fields as Recurrent Neural Networks. http://crfasrnn.torr.vision/

cs231n.github.io

Public facing notes page

cyclegan

Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more (from UC Berkeley)

dapper

Data Assimilation Package in Python for Experimental Research (DAPPER)

deconvnet

DeconvNet : Learning Deconvolution Network for Semantic Segmentation

deep-q-drive

repo for simple deep q-learning driving game

deep-route

Training a deep FCN network in PyTorch to route circuit layouts.

deep-theano-rnn-lstm-car

Pack of Drones: Layered reinforcement learning (Q-learning w/ RNN) for complex "hunt" behaviors

deepmimic

Motion imitation with deep reinforcement learning.

deepocclusion

deeprl-agents

A set of Deep Reinforcement Learning Agents implemented in Tensorflow.

dexmv-sim

DexMV: Imitation Learning for Dexterous Manipulation from Human Videos, ECCV 2022

dh

Experiments for using a differentiable Denavit-Hartenberg loss to improve the speed and stability of learning robot control policies. New work on identifying DH parameters from experience. Ongoing research.

diffcvgp

Webpage for the proposed workshop on differentiable vision, graphics, and physics